Writing log71 posts289 tagslatest Jun 29, 2026
Openai.
Latest posts
InstructGPT (2022) Paper Notes
Paper notes on InstructGPT covering its core method — the three-step RLHF recipe (SFT → reward model → PPO) — the alignment result where a 1.3B model beats 175B GPT-3, gains in truthfulness and toxicity, the alignment tax and PPO-ptx, and the limitations.
GPT-3 (2020) Paper Notes
Paper notes on GPT-3 covering its core ideas: 175B scaling, in-context learning (zero/one/few-shot), weighted-sampling training data, headline benchmark numbers, and the data-contamination and bias limitations.
GPT-2 (2019) Paper Notes
Paper notes on GPT-2 covering its core ideas: decoder-only Transformer scaling, WebText, next-token prediction, zero-shot task transfer, and the staged release controversy.